Hi, I'm Volkan Doğan 👋

Computer Vision Engineer | Deep Learning | Edge AI

View CV

As a Computer Vision Engineer with 8+ years of experience, I specialize in building real-time embedded systems using image processing and deep learning. My expertise covers the entire AI model development lifecycle—from design and training to optimization and deployment across diverse hardware platforms. I am primarily focused on delivering optimized, resource-efficient solutions for embedded and edge devices. My practical experience includes achieving massive model size reductions (up to 95%) for production systems and writing and filing a US patent application in Multi-Camera Synchronization and Human Pose Estimation.

This page serves as a hub for my professional journey, skills, and contributions to the field. Feel free to use the interactive chat below to learn more!

Interactive Q&A Chat 💬

Important Note:This is an experimental RAG implementation using a small Edge AI model. Responses are generated solely from the CV text provided in the prompt. We cannot guarantee absolute accuracy or currency of every statement. The official PDF CV is the definitive source of information.

This chat connects to a small LLM model. Feel free to ask about my professional background!

Education

  • MSc in Cognitive Science, 2023
    Middle East Technical University
  • BSc in Electrical - Electronics Engineering, 2017
    Middle East Technical University

🛠️ Skills & Expertise

💻Programming Languages
  • Python: Developing deep learning pipelines—training, testing, experimentation, proof-of-concept, algorithm development, and verification.
  • C++: Deployment on edge devices; integration with C/C++ codebases for production systems.
  • Matlab: Numerical computing, algorithm development, data visualization, and mathematical modeling.
🤖Deep Learning & Computer Vision
  • PyTorch / TensorFlow / Keras: Building, training, testing, evaluating neural networks.
  • OpenCV / NumPy: Image processing and numerical operations.
  • Object Detection, Semantic Segmentation, 2D/3D Human Pose Estimation, Anomaly Detection
  • Radar Spectrogram Analysis: Deep learning and signal processing for radar data.
  • Optical Design / Camera Calibration: Optical system design, lens selection, and calibration techniques.
  • Blender: 3D simulations, synthetic data generation for deep learning models, and optical design, including scripting with Python bpy.
  • V7 Darwin: Image/video annotation, data management, and annotation team management.
📦Edge & Embedded Platforms
  • Nvidia Jetson: Deploying AI and ML projects for edge computing.
  • Rockchip: AI/ML solutions for embedded and IoT applications.
  • Xilinx FPGA (Vivado SDK/RTL/HLS): FPGA algorithm design and development.
  • TensorRT / TVM: Model optimization for efficient inference.
  • GStreamer: Media-handling components and pipelines for streaming.
⚙️Engineering, Tools & Other
  • Linux: Main development environment (local and remote workspaces).
  • Git / SVN: Version control for team collaboration and code management.
  • Data pipeline automation: Automated annotation and data management using V7 Darwin and custom Python scripts.
  • C++ system-level algorithms: Core parameter processing and high-precision tracking.
  • Jira / Confluence / Office: Project management, documentation, and productivity tools.

(Detailed information is available in the 'View Resume' link on top of the page)